Inference code for Llama models

Generate cochleagrams natively in Python. Ported from Josh McDermott's MATLAB code.

We have released the code and demo program required for LLM with self-verification

Code for the paper "Evaluating Large Language Models Trained on Code"

Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""

Enhanced fork of SWE-bench, tailored for OpenDevin's ecosystem.

A concrete syntax tree parser and serializer library for Python that preserves many aspects of Python's abstract syntax tree

A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 30.67% tasks (pass@1) in SWE-bench lite and 38.40% tasks (pass@1) in SWE-bench verified wi…

Task-based Agentic Framework using StrictJSON as the core

Reasoning with Language Model is Planning with World Model

[ICLR 2024] SWE-Bench: Can Language Models Resolve Real-world Github Issues?

A Zsh theme

Agentless🐱: an agentless approach to automatically solve software development problems

A small Arduino library for GSM modules, that just works

Reference implementation for DPO (Direct Preference Optimization)

unofficial implementation of the CoT-decoding method for extract cot paths in an unsupervised way

Flow of Reasoning: Efficient Training of LLM Policy with Diverse Thinking

[EMNLP 2023, Findings] GRACE: Discriminator-Guided Chain-of-Thought Reasoning

SGLang is a fast serving framework for large language models and vision language models.

A library for advanced large language model reasoning

Code for MambaVC: Learned Visual Compression with Selective State Spaces

ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

Perceptual Metrics of Audio - perceptually relevant loss function. DPAM and CDPAM

A Very Low-Bitrate Codec for Speech Compression

Personal portfolio website. https://jeffersonyu1.github.io/

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…

Wireless IoT project